© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11046
    Prev
    Next
    INDEX
    Explanations

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Detaylı
    -0.20
    ÅŁeh
    -0.19
     ÅļwiÄĻt
    -0.18
     mükem
    -0.18
    Hugh
    -0.18
    çIJħ
    -0.17
    abo
    -0.17
     uçu
    -0.17
    char
    -0.17
    mız
    -0.17
    POSITIVE LOGITS
    ãģ¨ãģĦãģ£ãģŁ
    0.19
    หà¸į
    0.19
     Lawn
    0.18
    æĽĿ
    0.18
     deren
    0.18
    çīĪæĿĥå½ĴåİŁ
    0.18
    èĵĵ
    0.17
     Pets
    0.17
    reuse
    0.17
     Submitted
    0.17
    Activations Density 0.108%

    No Known Activations